arXiv subjects

Dongju Shin

Publications and source records attributed to Dongju Shin.

6 recordsLinked to original sources

arXiv2024

Minimal grid diagrams of the prime knots with crossing number 14 and arc index 13, 14

There are 46,972 prime knots with crossing number 14. Among them 19,536 are alternating and have arc index 16. Among the non-alternating knots, 17, 477, and 3,180 have arc index 10, 11, and 12, respectively. The remaining 23,762 have arc index 13 or 14. There are none with arc index smaller than 10 or larger than 14. We obtained 8,027 knots having arc index 13 and 15,735 knots having arc index 14. We show them by their minimal grid diagrams.

math.GT↗

arXiv2024

DeepJEB: 3D Deep Learning-based Synthetic Jet Engine Bracket Dataset

Recent advances in artificial intelligence (AI) have impacted various fields, including mechanical engineering. However, the development of diverse, high-quality datasets for structural analysis remains a challenge. Traditional datasets, like the jet engine bracket dataset, are limited by small sample sizes, hindering the creation of robust surrogate models. This study introduces the DeepJEB dataset, generated through deep generative models and automated simulation pipelines, to address these limitations. DeepJEB offers comprehensive 3D geometries and corresponding structural analysis data. Key experiments validated its effectiveness, showing significant improvements in surrogate model performance. Models trained on DeepJEB achieved up to a 23% increase in the coefficient of determination and over a 70% reduction in mean absolute percentage error (MAPE) compared to those trained on traditional datasets. These results underscore the superior generalization capabilities of DeepJEB. By supporting advanced modeling techniques, such as graph neural networks (GNNs) and convolutional neural networks (CNNs), DeepJEB enables more accurate predictions in structural performance. The DeepJEB dataset is publicly accessible at: https://www.narnia.ai/dataset.

cs.CG↗

arXiv2024

Learning Design Preferences through Design Feature Extraction and Weighted Ensemble

Design is a factor that plays an important role in consumer purchase decisions. As the need for understanding and predicting various preferences for each customer increases along with the importance of mass customization, predicting individual design preferences has become a critical factor in product development. However, current methods for predicting design preferences have some limitations. Product design involves a vast amount of high-dimensional information, and personal design preference is a complex and heterogeneous area of emotion unique to each individual. To address these challenges, we propose an approach that utilizes dimensionality reduction model to transform design samples into low-dimensional feature vectors, enabling us to extract the key representational features of each design. For preference prediction models using feature vectors, by referring to the design preference tendencies of others, we can predict the individual-level design preferences more accurately. Our proposed framework overcomes the limitations of traditional methods to determine design preferences, allowing us to accurately identify design features and predict individual preferences for specific products. Through this framework, we can improve the effectiveness of product development and create personalized product recommendations that cater to the unique needs of each consumer.

cs.HC↗

arXiv2023

Performance Comparison of Design Optimization and Deep Learning-based Inverse Design

Surrogate model-based optimization has been increasingly used in the field of engineering design. It involves creating a surrogate model with objective functions or constraints based on the data obtained from simulations or real-world experiments, and then finding the optimal solution from the model using numerical optimization methods. Recent advancements in deep learning-based inverse design methods have made it possible to generate real-time optimal solutions for engineering design problems, eliminating the requirement for iterative optimization processes. Nevertheless, no comprehensive study has yet closely examined the specific advantages and disadvantages of this novel approach compared to the traditional design optimization method. The objective of this paper is to compare the performance of traditional design optimization methods with deep learning-based inverse design methods by employing benchmark problems across various scenarios. Based on the findings of this study, we provide guidelines that can be taken into account for the future utilization of deep learning-based inverse design. It is anticipated that these guidelines will enhance the practical applicability of this approach to real engineering design problems.

math.OC↗

arXiv2023

Topology Optimization via Machine Learning and Deep Learning: A Review

Topology optimization (TO) is a method of deriving an optimal design that satisfies a given load and boundary conditions within a design domain. This method enables effective design without initial design, but has been limited in use due to high computational costs. At the same time, machine learning (ML) methodology including deep learning has made great progress in the 21st century, and accordingly, many studies have been conducted to enable effective and rapid optimization by applying ML to TO. Therefore, this study reviews and analyzes previous research on ML-based TO (MLTO). Two different perspectives of MLTO are used to review studies: (1) TO and (2) ML perspectives. The TO perspective addresses "why" to use ML for TO, while the ML perspective addresses "how" to apply ML to TO. In addition, the limitations of current MLTO research and future research directions are examined.

cs.LG↗

arXiv2019

A Single Multi-Task Deep Neural Network with Post-Processing for Object Detection with Reasoning and Robotic Grasp Detection

Recently, robotic grasp detection (GD) and object detection (OD) with reasoning have been investigated using deep neural networks (DNNs). There have been works to combine these multi-tasks using separate networks so that robots can deal with situations of grasping specific target objects in the cluttered, stacked, complex piles of novel objects from a single RGB-D camera. We propose a single multi-task DNN that yields the information on GD, OD and relationship reasoning among objects with a simple post-processing. Our proposed methods yielded state-of-the-art performance with the accuracy of 98.6% and 74.2% and the computation speed of 33 and 62 frame per second on VMRD and Cornell datasets, respectively. Our methods also yielded 95.3% grasp success rate for single novel object grasping with a 4-axis robot arm and 86.7% grasp success rate in cluttered novel objects with a Baxter robot.

cs.CV↗